GSAP: A Global Structure Attention Pooling Method for Graph-Based Visual Place Recognition

Yukun Yang,Bo Ma,Liang Zhao,Shoudong Huang,Xiangdong Liu

doi:10.3390/rs13081467

Yukun Yang, Bo Ma + Show 3 more

Open Access

https://doi.org/10.3390/rs13081467

Copy DOI

Abstract

The Visual Place Recognition problem aims to use an image to recognize the location that has been visited before. In most of the scenes revisited, the appearance and view are drastically different. Most previous works focus on the 2-D image-based deep learning method. However, the convolutional features are not robust enough to the challenging scenes mentioned above. In this paper, in order to take advantage of the information that helps the Visual Place Recognition task in these challenging scenes, we propose a new graph construction approach to extract the useful information from an RGB image and a depth image and fuse them in graph data. Then, we deal with the Visual Place Recognition problem as a graph classification problem. We propose a new Global Pooling method—Global Structure Attention Pooling (GSAP), which improves the classification accuracy by improving the expression ability of the Global Pooling component. The experiments show that our GSAP method improves the accuracy of graph classification by approximately 2–5%, the graph construction method improves the accuracy of graph classification by approximately 4–6%, and that the whole Visual Place Recognition model is robust to appearance change and view change.

Highlights

Given a sequence of images captured from different places, the images of the same place should be found, which is the Visual Place Recognition (VPR) problem [1]
As the Graph Neural Network (GNN) has shown advantages in dealing with graph data [16], we use the GNN model to complete the classification task, and we propose a novel graph Global Pooling method to improve the classification accuracy
To improve the expression ability of the GNN architecture, we propose a Global Pool method—Global Structure Attention Pooling

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. With the development of robotics and computer vision in recent years, improvement in the accuracy of localization and mapping is urgently needed. Given a sequence of images captured from different places, the images of the same place should be found, which is the Visual Place Recognition (VPR) problem [1]. VPR is a key component of image-based

Objectives

Results

Conclusion